Pinned Repositories
ChatGLM-Finetuning
基于ChatGLM-6B、ChatGLM2-6B、ChatGLM3-6B模型，进行下游具体任务微调，涉及Freeze、Lora、P-tuning、全参微调等
ChatGLM-Tuning
一种平价的chatgpt实现方案, 基于ChatGLM-6B + LoRA
GPT2-chitchat
GPT2 for Chinese chitchat/用于中文闲聊的GPT2模型(实现了DialoGPT的MMI**)
langchain-ChatGLM
langchain-ChatGLM, local knowledge based ChatGLM with langchain ｜ 基于本地知识库的 ChatGLM 问答
llama3-from-scratch
llama3 implementation one matrix multiplication at a time
LoRA
Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"
NLP-Loss-Pytorch
Implementation of some unbalanced loss like focal_loss, dice_loss, DSC Loss, GHM Loss et.al
P-tuning-v2
An optimized deep prompt tuning strategy comparable to fine-tuning across scales and tasks
PrefixTuning
Prefix-Tuning: Optimizing Continuous Prompts for Generation
SimCSE-Pytorch
中文数据集下SimCSE+ESimCSE的实现
zls130921's Repositories
zls130921/ChatGLM-Finetuning
基于ChatGLM-6B、ChatGLM2-6B、ChatGLM3-6B模型，进行下游具体任务微调，涉及Freeze、Lora、P-tuning、全参微调等
zls130921/ChatGLM-Tuning
一种平价的chatgpt实现方案, 基于ChatGLM-6B + LoRA
zls130921/GPT2-chitchat
GPT2 for Chinese chitchat/用于中文闲聊的GPT2模型(实现了DialoGPT的MMI**)
zls130921/langchain-ChatGLM
langchain-ChatGLM, local knowledge based ChatGLM with langchain ｜ 基于本地知识库的 ChatGLM 问答
zls130921/llama3-from-scratch
llama3 implementation one matrix multiplication at a time
zls130921/LoRA
Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"
zls130921/NLP-Loss-Pytorch
Implementation of some unbalanced loss like focal_loss, dice_loss, DSC Loss, GHM Loss et.al
zls130921/P-tuning-v2
An optimized deep prompt tuning strategy comparable to fine-tuning across scales and tasks
zls130921/PrefixTuning
Prefix-Tuning: Optimizing Continuous Prompts for Generation
zls130921/SimCSE-Pytorch
中文数据集下SimCSE+ESimCSE的实现